US 12,453,469 B2
Real-time detection of artifacts in ophthalmic images
Edwin Jay Sarver, Cookeville, TN (US); and Max Hall, Bradenton, FL (US)
Assigned to Alcon Inc., Fribourg (CH)
Filed by Alcon Inc., Fribourg (CH)
Filed on May 31, 2024, as Appl. No. 18/680,678.
Application 18/680,678 is a continuation of application No. 17/236,908, filed on Apr. 21, 2021, granted, now 12,035,970.
Claims priority of provisional application 63/135,125, filed on Jan. 8, 2021.
Prior Publication US 2024/0315552 A1, Sep. 26, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. A61B 3/103 (2006.01); G06T 5/00 (2006.01); G06T 7/00 (2017.01)
CPC A61B 3/103 (2013.01) [G06T 5/00 (2013.01); G06T 7/0012 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30041 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for processing image data for an ophthalmic procedure, the system comprising:
one or more processors; and
one or more memories storing instructions that are executable by the one or more processors to cause the system to perform operations including:
preprocessing an image of an eye of a patient;
generating, via a feature extraction stage of a two-stage machine learning model, a feature vector based on the image;
generating, via a classification stage of the two-stage machine learning model, an output vector based on the feature vector, the output vector representing a set of probabilities that the image includes a set of artifact types; and
determining, based on the output vector, an image quality of the image for display to an operator and indicating a probability that the image includes an artifact.